agentmods.dev

crucible: Instructions file for Claude Code

CLAUDE.md

crucible CLAUDE.md is an instructions file for Claude Code from jkitchin/crucible. It costs 1,101 tokens per session, scanned A, original, MIT.

A set of instructions for Crucible, a personal knowledge base that turns source documents into linked org-mode articles. Org-mode is a plain-text format for structured notes.

In plain words
What is it for?
It helps ingest primary sources, create summaries and topic articles, maintain links and indexes, and work with the knowledge graph database.
Why use it?
It explains where sources, notes, data, articles, and the SQLite database belong, making the knowledge-base workflow predictable for an AI assistant.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths.

This is jkitchin/crucible's own configuration. It tells Claude Code how to work on crucible itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything crucible configures →

not rated 12repo changed yesterday A scan 1,101 tokens original MIT
View source ↗ jkitchin/crucible
Reuse

Borrowing it

Nothing to install: this file belongs to jkitchin/crucible. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jkitchin/crucible/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jkitchin/crucible

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for crucible CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jkitchin/crucible/claude-md/github.svg)](https://agentmods.dev/instructions/jkitchin/crucible/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jkitchin/crucible/claude-md"><img src="https://agentmods.dev/badge/instructions/jkitchin/crucible/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for crucible CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jkitchin/crucible/claude-md"><img src="https://agentmods.dev/badge/instructions/jkitchin/crucible/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,101 This file is loaded in full into every session.
When invoked 1,101 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.01101 $0.01101
Opus 5.5 $0.00440 $0.00440
Sonnet 5.5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured yesterday against content hash 60b20c48ecc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crucible CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crucible: LLM-Compiled Knowledge Base

Overview

Crucible is a personal knowledge base where primary sources are ingested and distilled by an LLM into a structured, interlinked org-mode wiki. The wiki is the LLM's domain; humans rarely edit it directly.

Directory Layout

A crucible project keeps everything in .crucible/ at its root:

  • .crucible/sources/ - Primary source documents, organized by shareability:
    • external/ - Copyrighted material (PDFs, web articles). Gitignored.
      • pdfs/ - Academic papers, reports
      • web/ - Web clippings
    • notebooks/ - Your own ELN entries. NOT gitignored.
    • data/ - Your own experimental data. NOT gitignored.
  • .crucible/wiki/ - Distilled org-mode articles. Shareable. Organized by type:
    • concepts/ - Concept articles (one topic per file)
    • summaries/ - Per-source summaries
    • comparisons/ - Cross-source comparison articles
    • methods/ - Methodology articles
    • index.org - Auto-maintained master index
  • .crucible/crucible.db - Wiki graph database (SQLite). Tracks sources, articles, concepts, and links between them. Regenerable from wiki content.
  • .crucible/references.bib - Bibliography of ingested sources

~/.crucible/registry.json is the global registry of crucibles, so the home directory cannot itself be a project.

This repository holds the CLI (src/crucible/, entry point crucible.cli:cli), the agent skill (skills/crucible/), docs (docs/) and tests (tests/, run with pytest). Tests must point HOME and the registry at a temporary directory: crucible init runs install, which writes ~/.claude/.

Conventions

Org-Mode Articles

All wiki articles use org-mode format with scimax conventions:

  • Use #+TITLE: for the article title
  • Use #+FILETAGS: for categorization (include article type as a tag)
  • Use a properties drawer on the top heading with:
    • :ARTICLE_TYPE: - concept, summary, comparison, or method
    • :SOURCE_KEYS: - space-separated cite keys of primary sources
    • :STATUS: - draft, reviewed, or verified
    • :CREATED: - ISO date
  • Use org-ref citations: cite:key, citep:key, citet:key
  • Use [[file:path][description]] links for cross-references between articles
  • Write in narrative prose, not bulleted lists (unless content demands enumeration)

Read the full file on GitHub · 101 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday Changed · +9 lines · +133 tokens per session 60b20c48ecc1
  2. 2mo ago First seen · 92 lines · 968 tokens per session scan A 457697fd28d9

Subscribe to this mod's changes

crucible CLAUDE.md is an instructions file published in the GitHub repository jkitchin/crucible (12 stars, last pushed yesterday), licensed MIT. It adds 1,101 tokens to every session, about $0.0044 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude CodeLLMMemory and contextagent-skillsknowledge-baseorg-modewiki
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens